
import numpy as np
import pandas as pd
import nltk
import plotly.io as pio
import plotly.graph_objects as go
pio.templates.default = "plotly_white"
from sklearn.feature_extraction.text import CountVectorizer
from textblob import TextBlob
import plotly.express as px
import re
import string
from nltk.stem import WordNetLemmatizer
string.punctuation
from nltk.corpus import stopwords
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from plotly.subplots import make_subplots
from nltk.tokenize import word_tokenize
from nltk import pos_tag
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from textblob import TextBlob
import warnings
warnings.filterwarnings('ignore')
import seaborn as sns


def enable_plotly_in_cell():
  import IPython
  from plotly.offline import init_notebook_mode
  display(IPython.core.display.HTML('''<script src="/static/components/requirejs/require.js"></script>'''))
  init_notebook_mode(connected=False)


df = pd.read_csv ('dataset_semi.csv')
df


df.shape

(5922, 3)


print(f'We see the dataset has {df.shape[0]} observations and over {df.shape[1]} features.')

We see the dataset has 5922 observations and over 3 features.


df.head()


df.sample(5)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5922 entries, 0 to 5921
Data columns (total 3 columns):
 #   Column      Non-Null Count  Dtype 
---  ------      --------------  ----- 
 0   Text        5922 non-null   object
 1   Sentiment   5922 non-null   object
 2   Unnamed: 2  1 non-null      object
dtypes: object(3)
memory usage: 138.9+ KB


df.describe(include = 'all')


df.isnull().sum()

Text             0
Sentiment        0
Unnamed: 2    5921
dtype: int64


print(f'There are {df.duplicated().sum()} duplicated rows in the dataset.')

There are 43 duplicated rows in the dataset.


df[df['Text'].duplicated() == True]


df.loc[df['Text'] == 'Poor sync.']


df.loc[df['Text'] == 'very bad app']


df.drop_duplicates(keep=False, inplace=True)

df


df[df['Text'].duplicated() == True]


df.loc[df['Text'] == 'But the update on my iPhone has been hanging for hours.']


df.loc[df['Text'] == 'I\'m about to stop using it period!']


df.loc[df['Text'] == 'I\'m about to stop using it period!', "Sentiment"] = "negative"
df.loc[df['Text'] == 'I don\'t see any reason to install!', "Sentiment"] = "negative"
df.loc[df['Text'] == 'I\'m about to stop using it period!', "Sentiment"] = "negative"
df.loc[df['Text'] == 'But the update on my iPhone has been hanging for hours.', "Sentiment"] = "negative"
df.loc[df['Text'] == 'Habs already restarted does not bring anything', "Sentiment"] = "negative"
df.loc[df['Text'] == 'An example of what is possible without meeting on lots of lagg and curl ', "Sentiment"] = "negative"
df.loc[df['Text'] == 'Which incest developer has made such nonsense, heard executed or shared with the horses in 5 ', "Sentiment"] = "negative"
df.loc[df['Text'] == 'After this last update, when I put my e-mail and my password, from the error...', "Sentiment"] = "negative"
df.loc[df['Text'] == 'One more reason to consider when deciding why I should even keep this', "Sentiment"] = "negative"


df.drop_duplicates(keep=False, inplace=True)


df[df['Text'].duplicated() == True]


reviews = []
for index, row in df.iterrows():
    reviews.append(row['Text'])


punc = '''@1234567890!()-[]{};:'"\,<>./?@#$%^&*_~'''
reviewscleaned = []
for review in reviews:
    no_punct = ""
    for char in review:
       if char not in punc:
           no_punct = no_punct + char
    reviewscleaned.append(no_punct)


print(reviewscleaned)


import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
sw_nltk = stopwords.words('english')
sw_nltk1 = stopwords.words('spanish')
newreviews = []
for text in reviewscleaned:
    words = [word for word in text.split() if word.lower() not in (sw_nltk or sw_nltk1)]
    new_text = " ".join(words)
    newreviews.append(new_text)

[nltk_data] Downloading package stopwords to /root/nltk_data...
[nltk_data]   Unzipping corpora/stopwords.zip.


print(newreviews)


df2 = pd.DataFrame()
df2["Sentiment"] = df["Sentiment"]
df2["Text"] = newreviews
df2


sentiment = []
for index, row in df.iterrows():
    sentiment.append(row['Sentiment'])


from sklearn.feature_extraction.text import TfidfVectorizer
from nltk.corpus import stopwords
final_stopwords_list = stopwords.words('english') + stopwords.words('spanish')
input_vector = TfidfVectorizer (max_features=3000, min_df=6, max_df=0.8, stop_words=final_stopwords_list)
newreviews = input_vector.fit_transform(newreviews).toarray()


df2['Sentiment'].value_counts()

negative                                                                           2134
positive                                                                           2120
neutral                                                                            1565
 it adds a lot of great options by opening doors to new places and experiences.       1
-                                                                                     1
Name: Sentiment, dtype: int64


def remove_non_ascii(text):
    return re.sub(r'[^\x00-\x7F]', ' ', text)


df2['Sentiment'] = df2['Sentiment'].apply(remove_non_ascii)


df_filtered = df2.loc[df2['Sentiment'].isin(['positive', 'neutral', 'negative'])]


df_filtered['Sentiment'].value_counts()

negative    2134
positive    2120
neutral     1565
Name: Sentiment, dtype: int64


df3 = df_filtered


df3.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 5819 entries, 0 to 5921
Data columns (total 2 columns):
 #   Column     Non-Null Count  Dtype 
---  ------     --------------  ----- 
 0   Sentiment  5819 non-null   object
 1   Text       5819 non-null   object
dtypes: object(2)
memory usage: 136.4+ KB


df3['Sentiment'].isnull().sum

<bound method NDFrame._add_numeric_operations.<locals>.sum of 0       False
1       False
2       False
3       False
4       False
        ...  
5917    False
5918    False
5919    False
5920    False
5921    False
Name: Sentiment, Length: 5819, dtype: bool>


df3['Character_Length'] = df['Text'].str.len()
df3['Word_Length'] = df['Text'].str.count(' ') + 1


df3['Character_Length'].value_counts()

38      100
34       99
46       97
40       94
35       92
       ... 
2123      1
378       1
476       1
469       1
278       1
Name: Character_Length, Length: 353, dtype: int64


df3['Word_Length'].value_counts()

6      591
7      499
8      461
9      394
11     363
      ... 
100      1
68       1
149      1
101      1
71       1
Name: Word_Length, Length: 92, dtype: int64


df3.sample()


df3.head()


enable_plotly_in_cell()

sentiment = df3['Sentiment'].value_counts()

fig = px.pie(sentiment,
             values = sentiment.values,
             names = sentiment.index,
             color_discrete_sequence=px.colors.sequential.RdBu)
fig.update_traces(textinfo='percent+label',
                  marker = dict(line = dict(color = 'white', width = 5)))
fig.show()


text = ' '.join(df3['Text'])
wordcloud = WordCloud(background_color="white").generate(text)
plt.figure(figsize=(15,10))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.show()


def get_top_n_words(corpus, n=None):
    vec = CountVectorizer(stop_words = 'english').fit(corpus)
    bag_of_words = vec.transform(corpus)
    sum_words = bag_of_words.sum(axis=0)
    words_freq = [(word, sum_words[0, idx]) for word, idx in vec.vocabulary_.items()]
    words_freq =sorted(words_freq, key = lambda x: x[1], reverse=True)
    return words_freq[:n]


enable_plotly_in_cell()
common_words = get_top_n_words(df['Text'], 20)


df_unigram_20 = pd.DataFrame(common_words, columns = ['Word' , 'count']).sort_values(by="count",ascending=False).reset_index(drop=True)

fig = px.bar(df_unigram_20, x='Word', y='count')
fig.update_layout(
    title={
        'text': "Top 20 words across all cases",
        'x':0.5,
        'xanchor': 'center',
        'yanchor': 'top'})
fig.show()


def avg_word(sentence):
    words = sentence.split()
    if len(words) > 0:
      return (sum(len(word) for word in words)/len(words))
    return 0


def avg_word_length(df):
    df['avg_word'] = df['Text'].apply(lambda x: avg_word(x))
    print(df[['Text','avg_word']].head())


avg_word_length(df3)

                                                Text  avg_word
0  easy app use really quick easy set absolutely ...      5.30
1            drivers services exceptional since ever      7.00
2                                    rides enjoyable      7.00
3                                        Driver knew      5.00
4                     drivers child friendly patient      6.75

df3


def hash_tags(df):
    df['hashtags'] = df['Text'].apply(lambda x: len([x for x in x.split() if x.startswith('#')]))
    print(df[['Text','hashtags']].head())


hash_tags(df3)

                                                Text  hashtags
0  easy app use really quick easy set absolutely ...         0
1            drivers services exceptional since ever         0
2                                    rides enjoyable         0
3                                        Driver knew         0
4                     drivers child friendly patient         0


newreviews2 = input_vector.transform(df3['Text']).toarray()


sentiment2 = []
for index, row in df3.iterrows():
    sentiment2.append(row['Sentiment'])


from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(newreviews2,sentiment2,train_size=0.8)


from sklearn.ensemble import RandomForestClassifier
rf_classifier = RandomForestClassifier(n_estimators=200, random_state=42)
rf_classifier.fit(X_train, y_train)
rf_classifier_score = rf_classifier.score(X_train, y_train)
rf_classifier_score

0.9935553168635876


from sklearn.svm import SVC
svc_classifier = SVC(kernel='linear')
svc_classifier.fit(X_train, y_train)
svc_classifier_score = svc_classifier.score(X_train, y_train)
svc_classifier_score

0.8977443609022556


import sklearn.linear_model as sk
lr_classifier = sk.LogisticRegression(random_state=0, solver='liblinear', multi_class='ovr').fit(X_train, y_train)
lr_classifier_score = lr_classifier.score(X_train, y_train)
lr_classifier_score

0.8850698174006445


from sklearn.metrics import accuracy_score
rf_test = rf_classifier.predict(X_test)
accuracy_scorerf = accuracy_score(y_test, rf_test)
print(accuracy_scorerf)

0.7551546391752577


svc_test = svc_classifier.predict(X_test)
accuracy_scoresvc = accuracy_score(y_test, svc_test)
print(accuracy_scoresvc)

0.7792096219931272


lr_test = lr_classifier.predict(X_test)
accuracy_scorelr = accuracy_score(y_test,lr_test)
print(accuracy_scorelr)

0.7783505154639175


from sklearn.metrics import confusion_matrix, classification_report, accuracy_score


lr_confusion_matrix = confusion_matrix(y_test, lr_test)


sns.heatmap(lr_confusion_matrix, annot=True, fmt='g');  #annot=True to annotate cells, ftm='g' to disable scientific notation


svc_confusion_matrix = confusion_matrix(y_test, svc_test)


rf_confusion_matrix = confusion_matrix(y_test, rf_test)


lr_test

array(['negative', 'positive', 'negative', ..., 'negative', 'negative',
       'positive'], dtype='<U8')


enable_plotly_in_cell()
accuracy_of_models = {'SVC': svc_classifier_score,
                      'Random Forest': rf_classifier_score,
                      'Logistic Regression': lr_classifier_score}


fig = px.bar(x = list(accuracy_of_models.keys()), y= list(accuracy_of_models.values()),
             color = list(accuracy_of_models.values()),
             width = 800, height = 400,
             color_discrete_sequence=px.colors.qualitative.G10,
             labels={'x':'Classifier', 'y':'Accuracy'}, text_auto=True)


fig.update_layout(title='Accuracy performance of classification models')
fig.show()


confusion_matrix_of_models = {'SVC': svc_confusion_matrix,
                      'Random Forest': rf_confusion_matrix,
                      'Logistic Regression': lr_confusion_matrix}


enable_plotly_in_cell()
scores = [accuracy_scorerf, accuracy_scoresvc, accuracy_scorelr]

best_score = max(scores)
best_model = ''

for key, value in accuracy_of_models.items():
    best_model = key
    fig = px.imshow(confusion_matrix_of_models[key], text_auto=True, aspect="auto",
                    color_continuous_scale='viridis',
                    labels=dict(x="Actual", y="Prediction"))

    fig.update_layout(title = f'{key} Matrix', height=500, width=800)
    fig.show()

    confusion_matrix_of_models.pop(key)


best_score

0.7792096219931272


from IPython.display import Markdown


Markdown(f"""
#### From the results above we can see that {best_model} perfoms best with the highest accuracy of {round(best_score * 100, 2)}%""")

df3


new_entry = {'Text': "None", 'Sentiment': 'negative', "Unnamed: 2": np.NaN,'Character_Length': np.NaN, 'Word_Length': np.NaN}
df3.loc[578] = new_entry
df3.loc[1837] = new_entry


percent_sampled = 27
sample_df = df3.sample(frac = percent_sampled/100)


sample_df


df3.loc[df3.Text.isin(sample_df.Text), "Sentiment"] = "None"

df3


df3.head(25)


from sklearn.linear_model import LogisticRegression


labeled_data = df3[df3['Sentiment'] != 'None']
unlabeled_data = df3[df3['Sentiment'] == 'None']


unlabeled_data.sample(20)


labeled_data.sample(20)


labeled_data['Sentiment']

0       positive
1       positive
2       positive
4       positive
8       positive
          ...   
5919    positive
5920    negative
5921    negative
578     negative
1837    negative
Name: Sentiment, Length: 4242, dtype: object


sentiment_labelled = []
for index, row in labeled_data.iterrows():
    sentiment_labelled.append(row['Sentiment'])


X = input_vector.transform(labeled_data['Text']).toarray()
y = sentiment_labelled


import sklearn.linear_model as sk
model = sk.LogisticRegression(random_state=0, solver='liblinear', multi_class='ovr').fit(X, y)
model_score = model.score(X, y)
model_score

0.8781235266383781


df4 = df3


X_unlabeled = input_vector.transform(unlabeled_data['Text']).toarray()
predicted_labels = model.predict(X_unlabeled)


df4['original'] = df3['Sentiment']
df4.loc[df4['Sentiment'] == 'None', 'Sentiment'] = predicted_labels
df4['predicted'] = df4[['Sentiment']]
df4['Sentiment'] = df3[['Sentiment']]


df5 = df4[['Sentiment', 'original', 'predicted']]
df5


def ConvertSentiment(score):
  if score == 'positive':
    return 1
  elif score == 'neutral':
    return 0
  else:
    return 2
  return score


df5['Sentiment'] = df5['Sentiment'].apply(ConvertSentiment)
df5['predicted']  = df5['predicted'].apply(ConvertSentiment)


df5.head(60)


from sklearn.metrics import mean_squared_error

predicted_values = df5['predicted']
actual_values = df5['Sentiment']

mse = mean_squared_error(actual_values, predicted_values)
rmse = mse ** 0.5

print("Mean Squared Error (MSE):", mse)
print("Root Mean Squared Error (RMSE):", rmse)

Mean Squared Error (MSE): 0.0
Root Mean Squared Error (RMSE): 0.0


import joblib


joblib.dump(input_vector, 'vector.pkl')

['vector.pkl']


joblib.dump(model, 'senitment_analysis.pkl')

['senitment_analysis.pkl']


test_model = joblib.load('senitment_analysis.pkl')


result = test_model.score(X, y)
print(result)

0.8781235266383781

	Sentiment	Text	Character_Length	Word_Length	avg_word	hashtags
4457	negative	worst appit many time says please check connec...	59.0	10.0	5.375000	0.0
3759	neutral	real time exchange rates currently one option ...	92.0	17.0	5.545455	0.0
1060	positive	Gud useful online classes	39.0	7.0	5.500000	0.0
1925	negative	like stuff please ask language preferences Ind...	124.0	22.0	6.090909	0.0
4972	positive	oBsuzjsiznOAmsy visbss see mm es la PayPal hotel	57.0	11.0	5.125000	0.0
...	...	...	...	...	...	...
5473	negative	Theres reason streaming app take GB	56.0	12.0	5.000000	0.0
5484	neutral	Ive tried every option Gmail using phone number	60.0	11.0	5.000000	0.0
4883	negative	never get notifications pagesfrustrating mobil...	153.0	26.0	7.000000	0.0
1957	neutral	used possible choose nickname set rambling let...	130.0	25.0	6.000000	0.0
4268	negative	post posted anything bad	49.0	12.0	5.250000	0.0

	Sentiment	Text	Character_Length	Word_Length	avg_word
0	positive	easy app use really quick easy set absolutely ...	101.0	20.0	5.300000
1	positive	drivers services exceptional since ever	61.0	10.0	7.000000
2	positive	rides enjoyable	30.0	5.0	7.000000
3	None	Driver knew	28.0	6.0	5.000000
4	positive	drivers child friendly patient	45.0	7.0	6.750000
5	None	Quick easy use drivers quite friendly 😊	54.0	11.0	4.714286
6	None	Love Appits easy☮️shows person drive u Name	88.0	17.0	5.285714
7	None	Best drivers ever	17.0	3.0	5.000000
8	positive	Good travel app	24.0	5.0	4.333333
9	positive	Cabs r clean drivers	26.0	6.0	4.250000
10	positive	Love rides	14.0	3.0	4.500000
11	positive	Fast affordable efficient means get destinatio...	72.0	12.0	7.000000
12	positive	Perfect transport	17.0	2.0	8.000000
13	negative	rider vey wicked use add money	58.0	13.0	4.166667
14	positive	easiest way find transport safer	52.0	11.0	5.600000
15	positive	Safe travel	19.0	4.0	5.000000
16	positive	Always good ride good drivers	40.0	8.0	5.000000
17	positive	kids loved spacious ride	33.0	6.0	5.250000
18	positive	enjoyed ride	17.0	4.0	5.500000
19	None	Clean cars	11.0	2.0	4.500000
20	positive	Best service best prices	29.0	5.0	5.250000
21	positive	Fast convenient friendly drivers smile	52.0	8.0	6.800000
22	positive	never encounted bad experience even drivers pr...	75.0	12.0	7.142857
23	positive	convenient way moving around ever	42.0	7.0	5.800000
24	None	Nice rides ☺️	14.0	3.0	3.666667

	Sentiment	Text	Character_Length	Word_Length	avg_word
3715	None	Ive experienced simple quick cheap way send mo...	86.0	16.0	5.666667
5700	None	free love	36.0	10.0	4.000000
1144	None	ask youve today ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃ...	555.0	9.0	131.250000
3188	None	play game internet availible	40.0	7.0	6.250000
3622	None	support team tencent	28.0	5.0	6.000000
1071	None	badI cant install phone	35.0	7.0	5.000000
976	None	Bring seen sign shows messag seen without ente...	94.0	16.0	6.111111
5201	None	nice meet communicate others see friends	70.0	15.0	5.833333
4172	None	instant transfers international banks count do...	131.0	19.0	7.250000
1180	None	new layout fine feature loved gone	66.0	15.0	4.833333
1524	None	ÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ°ÃÂÃÂÃÂ...	16349.0	1.0	16349.000000
5047	None	lot ads like ads play next song	67.0	16.0	3.571429
1175	None	love since update everything	47.0	10.0	6.250000
1348	None	great app tution classes	37.0	8.0	5.250000
1776	None	one look antalya Alanya	52.0	10.0	5.000000
627	None	expensive dont know unsubscribe	55.0	10.0	7.000000
3745	None	weeks transfer arrived promised returne back a...	133.0	26.0	6.000000
4145	None	access search tab	24.0	6.0	5.000000
102	None	good app always useful updates ment ease user ...	130.0	22.0	5.800000
1402	None	Dated nonmaterial design UI lacks basic functi...	99.0	15.0	6.363636

	Sentiment	Text	Character_Length	Word_Length	avg_word
2963	positive	like fact took highlights Facebook	58.0	12.0	6.000000
5651	positive	love use also phone time working computer	93.0	22.0	5.000000
5320	positive	never used kind app im download app fun classe...	96.0	18.0	5.090909
1795	positive	previous version fits	26.0	4.0	6.333333
2397	neutral	get score coins	33.0	10.0	4.333333
3998	negative	media section select image option see chat lik...	98.0	20.0	5.333333
5448	positive	far enjoying bolt rides	43.0	9.0	5.000000
5489	positive	beauty journey lies drivers	46.0	9.0	6.000000
4759	positive	pretty good game ðð tho could use less b...	405.0	82.0	5.325000
4775	negative	Worst game ever game totally force spend money	58.0	11.0	4.875000
411	positive	worried easy every way Ive tried transfer mone...	124.0	21.0	6.272727
5696	positive	Surely best flexible time tracking apps	60.0	11.0	5.666667
5658	positive	point use app	25.0	6.0	3.666667
5880	negative	new update completely wiped LIKED PLAYLISTdo s...	98.0	15.0	6.400000
3431	negative	PREMIUM since since problem downloaded songs d...	155.0	30.0	6.300000
1683	positive	good lesson app designers	58.0	13.0	5.500000
1651	positive	Excellent content could much better designed i...	67.0	10.0	6.857143
3766	neutral	steps needed send money wallet	37.0	7.0	5.200000
4909	positive	good app although Easy fast love gave three star	71.0	17.0	4.444444
1667	negative	Pubg Mobile Good Game Butt hacker high fast gr...	114.0	20.0	5.000000

Sentiment Analysis on Text¶

Introduction¶

Overview¶

Columns¶

Problem Statement and Objective¶

About the Dataset¶

Solution and Analysis¶

Prepare the tools¶

Setup plotly¶

Load Data¶

Understanding the data¶

Check datatype and information regarding all different features¶

Data Pre-processing¶

Exploratory Data Analysis¶

Modelling¶

Reviewing Confusion Matrix based on Each Model¶

From the results above we can see that Logistic Regression perfoms best with the highest accuracy of 77.92%¶

Save Model¶

Test Model¶

Conclusion¶

Bibliography¶

Note from the Author¶

	Text	Sentiment	Unnamed: 2
0	Such an easy app to use, really quick and easy...	positive	NaN
1	The drivers and the services have been excepti...	positive	NaN
2	All rides have been enjoyable.	positive	NaN
3	Driver very knew where I was	neutral	NaN
4	most driver's are child friendly and patient.	positive	NaN
...	...	...	...
5917	My Liked Songs can only display all my songs i...	neutral	NaN
5918	Although it can be a little annoying in the fr...	negative	NaN
5919	It isn't about the catalogue..it's about the c...	positive	NaN
5920	Except for the fact that I can't open my downl...	negative	NaN
5921	This app stinks too many interruptions and upg...	negative	NaN

	Text	Sentiment	Unnamed: 2
1341	Its a good app for online study and mettings .	positive	NaN
1875	An extraordinary accuracy via gps , a must if ...	positive	NaN
4830	This is a nice app but many more features are ...	positive	NaN
3328	Very well succeeded, i Love it!	positive	NaN
2944	No latency or poor connection s	negative	NaN

	Text	Sentiment	Unnamed: 2
count	5922	5922	1
unique	5871	5	1
top	My music is only a search away!	negative	positive
freq	3	2186	1

	Text	Sentiment	Unnamed: 2
151	Poor sync.	negative	NaN
951	working on it	neutral	NaN
1599	I don't see any reason to install!	negative	NaN
1877	now after this update i can't dismiss ads..	negative	NaN
1884	The add songs feature in playlists doesnt let ...	negative	NaN
1889	slightly disappointed in you need to buy premi...	negative	NaN
1907	Too many ads, same ads repeated over and over ...	negative	NaN
1913	The app have to pay to choose your song of yo...	neutral	NaN
1930	Bring back my memories with old song with good...	neutral	NaN
1933	Whenever I go to play a track my app just cras...	negative	NaN
1996	GPs fail to show properly, drivers are mistake...	negative	NaN
2021	I'm about to stop using it period!	negative	NaN
2034	very bad app	negative	NaN
2043	But the update on my iPhone has been hanging f...	negative	NaN
2045	Habs already restarted does not bring anything	negative	NaN
2056	Love the new app! The design is super, and it'...	positive	NaN
2078	Chat heads don't appear sometimes but over all...	negative	NaN
2101	An example of what is possible without meeting...	negative	NaN
2353	Wont change my review until your CS contact me...	neutral	NaN
3546	Please make this game compatible with iPhone 6...	neutral	NaN
3554	No respond from them yet on that they are doin...	neutral	NaN
3677	From the functioncni app, totalne stilted and ...	positive	NaN
3834	Photos are sent in horrendous quality, with ch...	negative	NaN
3932	Premium is nice because it's affordable.	positive	NaN
4356	How in the hell does this app not have dark mo...	neutral	NaN
4364	Facebook changed a lot through years.	neutral	NaN
4374	Which incest developer has made such nonsense,...	negative	NaN
4383	After this last update, when I put my e-mail a...	neutral	NaN
4384	Unfortunately, despite almost weekly updates o...	negative	NaN
4427	One more reason to consider when deciding why ...	neutral	NaN
4430	What will it take to remove this feature?	neutral	NaN
4434	I've been using the app for several years now.	neutral	NaN
4528	Help, unwrite me off the paid version! Please!	negative	NaN
4910	I watch all Yt, etc., only through here to not...	negative	NaN
5323	I am 19 and why can't i sing up	neutral	NaN
5358	My music is only a search away!	neutral	NaN
5399	Wish the app will allow you to add another rou...	positive	NaN
5454	Your estimated time of arrival is always not c...	negative	NaN
5459	I call him, message him, he doesn't pick up th...	negative	NaN
5526	My music is only a search away!	neutral	NaN
5528	My songs doesn't play automatically.I already ...	negative	NaN
5529	This used to be a wonderful App.	positive	NaN
5530	Lately it has been very slow and unresponsive.	negative	NaN
5531	It barely functions for me and many other user...	negative	NaN
5532	So unfortunately at this time I would not reco...	negative	NaN
5533	Very nice app enjoy it very much	positive	NaN
5534	Spotify has their own DC Universe access deals...	neutral	NaN
5535	It's official, I hate Spotify multiple people ...	negative	NaN
5536	Very disappointing to have drivers pick a requ...	negative	NaN
5538	I just luv their customer service	positive	NaN
5581	This update doesn t allow me to see my homepag...	negative	NaN

	Text	Sentiment	Unnamed: 2
1974	But the update on my iPhone has been hanging f...	neutral	NaN
2043	But the update on my iPhone has been hanging f...	negative	NaN

	Text	Sentiment	Unnamed: 2
2010	I'm about to stop using it period!	neutral	NaN
2021	I'm about to stop using it period!	negative	NaN